Litellm gemini api base update

[Sameerlite]

Add proper api_base support for Gemini models in LiteLLM proxy

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
🐛 Bug Fix

Changes

Added better URL construction for gemini. Now when you provide API BASE, it will add the model defined in the config with the api base and endpoint. ** This change doesn't break the earlier functionality of when api_base is not provided the api request goes to - https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent?key=*****xQMg . The vertex_ai provider config also works as earlier.

Testing

# Now correctly constructs: https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent
response = litellm.completion(
    model="gemini/gemini-2.5-flash-lite", 
    messages=[{"role": "user", "content": "Hello!"}],
    api_base="https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta"
)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Ready	Preview	Comment	Sep 16, 2025 10:18am